garrytan · rafaelreis-r · May 3, 2026 · May 3, 2026 · May 3, 2026 · May 18, 2026
diff --git a/README.md b/README.md
@@ -585,6 +585,32 @@ Query
 
 Keyword alone misses conceptual matches. Vector alone misses exact phrases. RRF gets both. Search quality is benchmarked and reproducible: `gbrain eval --qrels queries.json` measures P@k, Recall@k, MRR, and nDCG@k. A/B test config changes before deploying them.
 
+### Non-English brains (FTS language config)
+
+The Postgres full-text search tokenizer is configurable via `GBRAIN_FTS_LANGUAGE`. Defaults to `english`. Set it to any text-search configuration that exists in your Postgres instance:
+
+```bash
+export GBRAIN_FTS_LANGUAGE=portuguese     # uses built-in portuguese stemmer
+export GBRAIN_FTS_LANGUAGE=spanish        # built-in spanish stemmer
+export GBRAIN_FTS_LANGUAGE=pt_br          # custom config (e.g. unaccent + portuguese)
+```
+
+List available configs: `psql -c "SELECT cfgname FROM pg_ts_config"`. To create a custom accent-insensitive Portuguese config, see [docs/guides/multi-language-fts.md](docs/guides/multi-language-fts.md).
+
+Both the **query side** (`websearch_to_tsquery`) and the **write side** (the trigger functions that populate `pages.search_vector` and `content_chunks.search_vector`) honor `GBRAIN_FTS_LANGUAGE`. On first install, schema migration v33 reads the env var and creates trigger functions in the configured language; subsequent inserts/updates tokenize using that setting.
+
+To change language on a brain that has already run v33, use the dedicated CLI command:
+
+```bash
+export GBRAIN_FTS_LANGUAGE=portuguese
+gbrain reindex-search-vector --dry-run    # preview row counts
+gbrain reindex-search-vector --yes        # recreate triggers + backfill
+```
+
+The command is idempotent (re-running with the same language is a no-op for vector content) and uses the same recreate-and-backfill primitives as v33.
+
+For accent-insensitive Portuguese (`pt_br`), see [docs/guides/multi-language-fts.md](docs/guides/multi-language-fts.md) for the `unaccent` + portuguese stemmer recipe.
+
 ## Why it works: many strategies in concert
 
 The brain isn't one trick. Every retrieval question goes through ~20 deterministic

diff --git a/TODOS.md b/TODOS.md
@@ -1,6 +1,5 @@
 # TODOS
 
-
 ## v0.35.6.0 floor-ratio gate follow-ups (v0.36.x+)
 
 - [ ] **v0.36.x: Run gbrain-side floor-ratio ablation before flipping any mode-bundle default.** v0.35.6.0 ships the gate default-off (`MODE_BUNDLES[*].floor_ratio = undefined`) because the SkyTwin labeled-retrieval ablation that surfaced the regression isn't reproducible on gbrain's own eval surfaces from outside. Before any mode-bundle default flip, run the gate at `floor_ratio: undefined`, 0.85, 0.90, 0.95 across `gbrain eval longmemeval`, `gbrain eval whoknows`, `gbrain eval suspected-contradictions`, and the BrainBench-Real replay (sibling gbrain-evals repo). Quantify per-mode P@k / R@k / nDCG@k / top-1 stability deltas. Look for: regression on queries that genuinely need the long-tail boost (specific entity lookups, low-frequency topics) vs improvement on queries where weak-overlap pages were leapfrogging. The corpus-level finding determines whether tokenmax (most exposure to the failure mode) should flip first, or whether the gate stays a per-call opt-in indefinitely. Filed during v0.35.6.0 codex outside-voice review.
@@ -11,14 +10,12 @@
 
 - [ ] **v0.36.x: Reranker top-N expansion when floor-ratio narrows the candidate pool.** Floor-ratio can suppress a legitimate candidate that would have made it to the reranker's top-N. Sanity check after the v0.36 ablation: if tokenmax with `floor_ratio: 0.85` and `reranker_top_n_in: 30` shows the reranker seeing a meaningfully different set than without the gate, consider expanding `reranker_top_n_in` when floor is set (e.g. 30 → 40) so the reranker still has 30 floor-eligible candidates to reorder. Cheap mitigation if the data supports it. Not a blocker.
 
-
 ## dreamy-thompson wave follow-ups (v0.36.x)
 
 - [ ] **v0.36.x: runThink full rewrite — drop ThinkLLMClient indirection.** v0.36's fix(think) wave landed a gateway-backed adapter at `src/core/think/index.ts:225-251` so `gbrain config set anthropic_api_key` works over MCP stdio (closed #952). The adapter routes through `gateway.chat()` but `runThink` still carries the `ThinkLLMClient` interface as the test seam — it's the last LLM-using path that doesn't use the canonical `__setChatTransportForTests` seam v0.31.12 established for chat/embed. Cleanup: drop `ThinkLLMClient`, drop the `opts.client` injection point, migrate the 12+ existing tests (`test/think-pipeline.serial.test.ts:144,181,222`, `test/think-gateway-adapter.test.ts`, plus 9+ others that stub the interface) to `__setChatTransportForTests`. Pros: codebase consistency, one fewer test-stub pattern, easier to add provider switching for think once it routes through gateway natively. Cons: 12+ test files need migration. Blocked by: v0.36 wave landing on master (so the adapter exists to lean on while migrating tests). Plan reference: D5 + D7 in `~/.claude/plans/ok-i-spun-up-dreamy-thompson.md`.
 
 - [ ] **v0.36.x: Supabase parity test fixture for `applyForwardReferenceBootstrap`.** v0.36 fixed the underlying bug (bootstrap now uses the DDL connection from `initSchema` so probes run inside the advisory-lock scope) per codex P1 from /ship adversarial review. What remains is the TEST FIXTURE that proves it: the new pre-v18/pre-v34/pre-v60 E2E tests run against local Docker Postgres but not against Supabase-shape pooler topology (transaction pooler + statement_timeout). Real Supabase upgrades have failed multiple times on this exact connection-topology divergence (#699, #820 lineage). Fix: a test fixture that exercises the probe path against deriveDirectUrl + transaction pooler + statement_timeout. Cons: requires Supabase fixture infra OR careful mocking of the connection-selection logic in `db.ts`'s `getDDLConnection` path.
 
-
 ## kinshasa-v3 follow-ups (v0.35.4.0)
 
 - [ ] **v0.36.x: Fix `supervisor-audit.ts:77` `readSupervisorEvents` to use the dual-week-aware pattern from `stub-guard-audit.ts:readRecentStubGuardEvents`.** The supervisor reader only reads the current ISO-week file, so a 24h sliding window across Monday 00:00 UTC silently loses Sunday's events (they're in last week's file). The new stub-guard reader in v0.35.4.0 fixes this for its own audit log by reading BOTH current and previous week files before timestamp-filtering — the supervisor reader should adopt the same shape. Pin with a unit test that uses a fake-clock fixture set to "Monday 00:01 UTC" with a Sunday 23:55 event in the prior file. Filed during v0.35.4.0 kinshasa-v3 codex outside-voice review.
@@ -29,7 +26,6 @@
 
 - [ ] **v0.36.x: Sweep the banned private-agent-name references out of `CHANGELOG.md`.** Three pre-existing lines in `CHANGELOG.md` (around lines 2537, 2606, 3304) reference the name that `scripts/check-privacy.sh` enforces against. Pre-existing on master, not introduced by v0.35.4.0; `CHANGELOG.md` is on the script's allow-list so master CI is green, but they still violate the spirit of CLAUDE.md's privacy rule (the allow-list is a meta-documentation exception, not a license to add new references). Replace with `your OpenClaw` or `Garry's OpenClaw` per the script's own suggestion text. Trivial cleanup PR. Filed during v0.35.4.0 privacy audit.
 
-
 ## embed --stale follow-ups (v0.34.4.0)
 
 - [ ] **v0.35.x: Concurrent NULL→non-NULL upsert race in `embed.ts:429-443` + `postgres-engine.ts:1231`'s `COALESCE(EXCLUDED.embedding, content_chunks.embedding)`.** Two `embed --stale` workers (or `embed --stale` racing with a sync that re-embeds the same chunk) can have the slower writer overwrite the faster one's fresher embedding. Window is small (20 workers, all from the same `listStaleChunks` snapshot) but exists. Tractable fix: a `WHERE content_chunks.embedded_at < EXCLUDED.embedded_at OR content_chunks.embedding IS NULL` predicate on the upsert. Out of scope for v0.34.4.0 because the upsert is not in the diff; pre-existing bug. Filed during v0.34.4.0 codex outside-voice review.
@@ -52,7 +48,6 @@
 
 - [ ] **v0.34.x: `hybrid.ts:223` explicit-pick refactor.** The SearchOpts rebuild manually picks fields from HybridSearchOpts. This is the bug shape that caused the original v0.34.1 P0 leak — a new SearchOpts field is silently dropped if not manually added here. The wave added `sourceId` + `sourceIds` to the pick; future fields will keep hitting this footgun. Fix: refactor to spread + TypeScript `Pick<>` helper that narrows HybridSearchOpts → SearchOpts type-safely.
 
-
 ## functional-area-resolver follow-ups (v0.32.3.0)
 
 - [ ] **v0.33.x: Dogfood `functional-area-resolver` on gbrain's own `skills/RESOLVER.md`** when it crosses ~12KB (currently 8KB). Apply the pattern to the Operational section first (largest). Filed during v0.32.3.0 CEO review.
@@ -1925,7 +1920,6 @@ flow + recovery messaging).
 **Depends on:** decision on whether to deprecate the bare name or dual-publish
 during a transition window.
 
-
 ## v0.32.6 follow-ups from PR #880 (gbrain-context post-Codex recalibration)
 
 These items were demoted from the PR #880 scope because they depend on

diff --git a/docs/UPGRADING_DOWNSTREAM_AGENTS.md b/docs/UPGRADING_DOWNSTREAM_AGENTS.md
@@ -537,4 +537,3 @@ To check what your fork is missing:
 ```bash
 diff <(grep -A3 "Based on gbrain" ~/<your-fork>/skills/brain-ops/SKILL.md) \
      <(grep "v[0-9]" ~/gbrain/skills/migrations/ | tail -3)
-```
diff --git a/skills/_brain-filing-rules.md b/skills/_brain-filing-rules.md
@@ -131,6 +131,56 @@ gbrain files restore <dir>                # Download back to local
 This ensures any derived brain page can be traced back to its original source,
 and large files don't bloat the git repo.
 
+## `docs/` — Workspace Document Index (v0.5, gdoc-ingest skill)
+
+The `docs/` directory is the canonical INDEX of Google Workspace documents
+(Docs / Sheets / Slides / PDFs in Drive) that Rafael cares about. Drive
+remains source of truth; the brain is the searchable index.
+
+### Path conventions
+
+| State | Slug pattern | Owner |
+|-------|--------------|-------|
+| Inbox (untriaged) | `docs/inbox/<slug>` | gdoc-ingest skill auto-creates |
+| Triaged (canonical) | `docs/<disciplina>/<tema>/<slug>` | Triage promotes after Rafael confirms |
+| Aggregated view | `docs/inbox` | Materialized view of pending items |
+| Templates | `docs/<disciplina>/_templates/<slug>` | Underscore prefix |
+| Concepts | `docs/concepts/<slug>` | Reusable principles (e.g. title-first-classification) |
+
+### Frontmatter contract
+
+All `docs/` pages MUST carry these frontmatter keys (see prds/gdoc-ingest):
+
+- `type: document`
+- `status: draft-index | oficial | draft | arquivado | obsoleto | stale-untriaged`
+- `kind: doc | sheet | slide | pdf | drive-file`
+- `disciplina` + `tema` (canonical taxonomy in TAXONOMY constant)
+- `secondary_tags: []` (other taxonomy matches in body)
+- `owner` (email)
+- `url_drive` (Drive link — source of truth)
+- `file_id` (Drive file ID for de-dup)
+- `mimetype` (MIME of the source file)
+- `last_modified_drive` + `indexed_at` (ISO timestamps)
+- `indexed_via: slack-paste | drive-crawler | manual-cli | e2e-test`
+- `raw_char_count` (extracted text length)
+- `is_meeting_doc: true` (if Google Meet transcript or Gemini Anotações)
+- `slide_stats` (for slides) OR `sheet_stats` (for sheets)
+
+### Filing rule for documents
+
+1. **Title-first classification** — the title decides disciplina/tema, not body keywords. (See `concepts/title-first-classification`.)
+2. **Iron Law** — every entity (person, project) mentioned with an existing brain page MUST get a back-link FROM that entity TO the doc page. Skill applies this automatically when `--commit` is used; only entities that ALREADY have pages get linked (notability gate).
+3. **Successor detection** — if title suggests a newer version (e.g. "Relatório Mar 2026" with "Relatório Feb 2026" already in brain), skill flags `successorOf` in payload. Triage decides if predecessor goes to `status: arquivado`.
+4. **No PII redaction at ingest** — fallback heuristic surfaces raw text. PII redaction is the LLM's responsibility at TRIAGE (sonnet-4-6).
+5. **Drive is source of truth** — NEVER edit content in brain page; brain is a read-only index. To change content, edit in Drive and re-ingest.
+
+### Triage workflow
+
+1. Cron `gdoc-inbox-triagem-ping` (sex 15h BRT) lists pending items in Slack.
+2. Rafael responds: ✅ confirma slug, ✏️ corrige tema, 🗑️ descarta, ou 🔗 marca como sucessor.
+3. On confirm: page moves from `docs/inbox/<slug>` to `docs/<disciplina>/<tema>/<slug>`, status changes to `oficial`.
+4. On stale (>60d in inbox): cron auto-tags `stale-untriaged`.
+
 ## Dream-cycle synthesize / patterns directories (v0.23)
 
 The `synthesize` and `patterns` phases of `gbrain dream` write to a

diff --git a/skills/academic-verify/SKILL.md b/skills/academic-verify/SKILL.md
@@ -208,7 +208,6 @@ doesn't, the trace speaks for itself.
   skill checks whether the cited claim is true
 - `skills/conventions/quality.md` — citation + back-link rules
 
-
 ## Contract
 
 This skill guarantees:

diff --git a/skills/archive-crawler/SKILL.md b/skills/archive-crawler/SKILL.md
@@ -303,7 +303,6 @@ scan_paths: ["paths from gbrain.yml"]
   the same primary-subject filing rule
 - `skills/conventions/quality.md` — citations, back-links, voice
 
-
 ## Contract
 
 This skill guarantees:

diff --git a/skills/concept-synthesis/SKILL.md b/skills/concept-synthesis/SKILL.md
@@ -238,7 +238,6 @@ This is heavy work. Run on a cadence, not on every signal:
 - `skills/voice-note-ingest/SKILL.md` — same for audio channels
 - `skills/idea-ingest/SKILL.md` — same for links / articles
 
-
 ## Contract
 
 This skill guarantees:
-Original file line number
+Diff line change
@@ Expand Up / @@ -537,4 +537,3 @@ To check what your fork is missing: @@
     ```bash
     diff <(grep -A3 "Based on gbrain" ~/<your-fork>/skills/brain-ops/SKILL.md) \
          <(grep "v[0-9]" ~/gbrain/skills/migrations/ | tail -3)
-    ```